Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14004
    Prev
    Next
    INDEX
    Explanations

    the prefix "poly-"

    oai_token-act-pair · gemini-2.0-flash

    poly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.62
    تقاوى
    -0.58
    хьтан
    -0.56
    caux
    -0.55
     beginnetje
    -0.50
    клопе
    -0.50
    sbericht
    -0.49
    ricul
    -0.49
    曖昧さ回避
    -0.48
     aDecoder
    -0.48
    POSITIVE LOGITS
    下载附件
    0.55
     resourceCulture
    0.52
     لعب
    0.51
    ClientSize
    0.50
     Actual
    0.50
    퀀
    0.50
    \{\\
    0.49
     Invisible
    0.49
     uParam
    0.48
     prezent
    0.48
    Activations Density 0.476%

    No Known Activations